PDF: Always call FPDFAvail_IsDocAvail() when loading.

pdf/pdfium/pdfium_engine.cc

 // Copyright (c) 2012 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #include "pdf/pdfium/pdfium_engine.h"
 
 #include <math.h>
 #include <stddef.h>
 #include <stdint.h>
 
@@ skipping 280 matching lines @@
   EnumFonts,
   MapFont,
   0,
   GetFontData,
   0,
   0,
   DeleteFont
 };
 #endif  // defined(OS_LINUX)
 
-PDFiumEngine* g_engine_for_unsupported;
+PDFiumEngine* g_engine_for_unsupported = nullptr;
 
 void Unsupported_Handler(UNSUPPORT_INFO*, int type) {
   if (!g_engine_for_unsupported) {
     NOTREACHED();
     return;
   }
 
   g_engine_for_unsupported->UnsupportedFeature(type);
 }
 
@@ skipping 730 matching lines @@
   if (!FPDFAvail_IsLinearized(fpdf_availability_)) {
     doc_loader_.RequestData(0, doc_loader_.document_size());
     return;
   }
 
   LoadDocument();
 }
 
 void PDFiumEngine::OnPendingRequestComplete() {
   if (!doc_ || !form_) {
+    DCHECK(fpdf_availability_);

[Lei Zhang, 2016/05/25 17:16:36]

I'm pretty sure OnPartialDocumentLoaded() has to be called before we can get to
this function.

[Wei Li, 2016/05/25 22:37:38]

Acknowledged.

     LoadDocument();
     return;
   }
 
   // LoadDocument() will result in |pending_pages_| being reset so there's no
   // need to run the code below in that case.
   bool update_pages = false;
   std::vector<int> still_pending;
   for (int pending_page : pending_pages_) {
     if (CheckPageAvailable(pending_page, &still_pending)) {
@@ skipping 1361 matching lines @@
   if (!password.empty()) {
     password_cstr = password.c_str();
     password_tries_remaining_--;
   }
   if (doc_loader_.IsDocumentComplete() &&
       !FPDFAvail_IsLinearized(fpdf_availability_)) {
     doc_ = FPDF_LoadCustomDocument(&file_access_, password_cstr);
   } else {
     doc_ = FPDFAvail_GetDocument(fpdf_availability_, password_cstr);
   }
+  if (!doc_) {
+    if (FPDF_GetLastError() == FPDF_ERR_PASSWORD)
+      *needs_password = true;
+    return false;
+  }
 
-  if (!doc_ && FPDF_GetLastError() == FPDF_ERR_PASSWORD)
-    *needs_password = true;
-
-  return !!doc_;
+  // Always call FPDFAvail_IsDocAvail() so PDFium initializes internal data
+  // structures.
+  int avail = FPDFAvail_IsDocAvail(fpdf_availability_, &download_hints_);

[Lei Zhang, 2016/05/25 17:16:36]

I decided to (potentially) call this a second time just after loading the
document instead, like we do in samples/pdfium_test.cc.

[Wei Li, 2016/05/25 22:37:38]

Would this approach be fragile? In samples/pdfium_test.cc, it uses a loop to
wait until it becomes available. FPDFAvail_IsDocAvail calls
CPDF_DataAvail::CheckDocStatus which requires to be called at least three times
to read the hint table. 

[Lei Zhang, 2016/06/14 17:53:56]

Whether FPDFAvail_IsDocAvail() ends up reading the hint table depends on the
document. I think the DCHECK assertion may be a bit strong and I will remove it.
The goal here is not to make sure it returns PDF_DATA_AVAIL. (though it probably
should for well-formed documents) Instead, we just want to make sure
FPDFAvail_IsDocAvail() gets called at least once, so it has a chance to progress
through the CheckDocStatus() calls.

I tested with a modified pdfium_test where I don't run it in a loop and it
works.

[Wei Li, 2016/06/14 23:33:42]

I think the fix is in right direction. But we need to be extra careful here. If
I understand correctly, if the pdf file is not available at this moment, the
subsequent LoadDocument/FPDFAvail_IsDocAvail will not be called any more since
doc_ is set already. 

+  DCHECK_EQ(PDF_DATA_AVAIL, avail);
+  return true;
 }
 
 void PDFiumEngine::GetPasswordAndLoad() {
   getting_password_ = true;
   DCHECK(!doc_ && FPDF_GetLastError() == FPDF_ERR_PASSWORD);
   client_->GetDocumentPassword(password_factory_.NewCallbackWithOutput(
       &PDFiumEngine::OnGetPasswordComplete));
 }
 
 void PDFiumEngine::OnGetPasswordComplete(int32_t result,
@@ skipping 1422 matching lines @@
   FPDF_DOCUMENT doc =
       FPDF_LoadMemDocument(pdf_buffer, pdf_buffer_size, nullptr);
   if (!doc)
     return false;
   bool success = FPDF_GetPageSizeByIndex(doc, page_number, width, height) != 0;
   FPDF_CloseDocument(doc);
   return success;
 }
 
 }  // namespace chrome_pdf